Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to different ideologies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     compound
    -0.65
     Saw
    -0.65
     income
    -0.64
     bush
    -0.64
     cross
    -0.63
     [*
    -0.62
     warr
    -0.61
     May
    -0.61
     tenant
    -0.61
     Jake
    -0.58
    POSITIVE LOGITS
    olog
    4.80
    OLOG
    2.49
    ologue
    2.41
    ologies
    2.26
    ologically
    2.05
    ological
    2.02
    ology
    2.00
    ologic
    1.96
    ologists
    1.92
    ologist
    1.77
    Act Density 0.012%

    No Known Activations